Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Gas turbine multi-sensor fault detection method based on hybrid method

A gas turbine and multi-sensor technology, which is applied in internal combustion engine testing, complex mathematical operations, design optimization/simulation, etc., can solve problems such as insensitivity of multi-sensor fault detection, and achieve the effect of strong promotion significance and improved detection accuracy.

Active Publication Date: 2021-10-01
HARBIN INST OF TECH +2
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Aiming at the insensitive problem of multi-sensor fault detection of existing gas turbines, the present invention provides a gas turbine multi-sensor fault detection method based on a hybrid method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Gas turbine multi-sensor fault detection method based on hybrid method
  • Gas turbine multi-sensor fault detection method based on hybrid method
  • Gas turbine multi-sensor fault detection method based on hybrid method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0075] In order to verify the effectiveness of the proposed method of the present invention, the following experiments are designed on the three-shaft gas turbine simulator set up now:

[0076] Gas turbine fuel flow q mfe Increase from 90% to 100% at a constant speed within 300s to indicate that the gas turbine is in a state of variable operating conditions. In the experiment, 7 sensors were selected as the sensors to be detected, respectively n H , n L , n P Low pressure compressor outlet temperature (T 1 ) and pressure (p 1 ) and high pressure compressor outlet temperature (T 2 ) and pressure (p 2 ). Fault is set at 100s when n L , n P and p 1 The bias failure of the three sensors occurred at the same time, and the severity of the failure was 1% of the parameters under the standard operation of the gas turbine, and the simulation time interval was 0.01s.

[0077] Based on the method proposed in the present invention, firstly, the parameter identification of the eq...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a gas turbine multi-sensor fault detection method based on a hybrid method, solves the problem that multi-sensor fault detection of an existing gas turbine is insensitive, and belongs to the technical field of gas turbine fault detection. The method comprises the following steps: S1, obtaining operation data of a gas turbine without faults, wherein the operation data comprises data of each sensor of the gas turbine; S2, establishing an equilibrium manifold expansion model of the gas turbine, and performing parameter identification by using data of each sensor to obtain a state equation and an observation equation which correspond to each sensor and are used for estimating the gas turbine by Kalman filtering; S3, performing optimal estimation on the state of the gas turbine by using measurement data of each sensor and the corresponding state equation and observation equation in the S2, and taking the obtained state quantity as a detection factor of the corresponding sensor; and S4, clustering and dividing the detection factors of all the sensors into two classes, wherein the sensors corresponding to the class with a small number of detection factors are fault sensors.

Description

technical field [0001] The invention relates to a gas turbine multi-sensor fault detection method based on a hybrid method, and belongs to the technical field of gas turbine fault detection. Background technique [0002] A gas turbine is a rotating machine consisting of a compressor, a combustion chamber, a turbine and a series of auxiliary systems, and is an important prime mover. It has been widely used in many fields such as power systems, aerospace, and ships, and is the core power equipment for efficient energy conversion and clean utilization in the 21st century and beyond. Gas turbine is known as "the jewel in the crown of industry". Its working principle and internal structure are very complicated, and its working environment is very harsh. It usually needs to monitor its operating status in real time, and use the monitoring data to monitor the status of the system. Condition monitoring requires the use of numerous sensors all over the gas turbine to collect unit op...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G01M15/05G06F30/20G06F17/16
CPCG01M15/05G06F30/20G06F17/16
Inventor 刘金福朱麟海龙振华任铭昊罗京刘鑫
Owner HARBIN INST OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com